Journal of Computer and Robotics
Volume:14 Issue: 1, Winter and Spring 2021

Link Prediction (LP) is one of the main research areas in Social Network Analysis (SNA). The problem of LP can help us understand the evolution mechanism of social networks, and it can be used in different applications such as recommendation systems, bioinformatics, and marketing. Social networks can be shown as a graph, and LP algorithms predict future connections by using previous network information. In this paper, a multi-wave cellular learning automaton (MWCLA) is introduced and used to solve the LP problem in social networks. The proposed model is a new CLA with a connected structure and a module of LAs in each cell where a cell module’s neighbors are its successors. In the MWCLA method for improving convergence speed and accuracy, multiple waves have been used parallelly in the network. By using multiple waves, different information of the network can be considered for predicting links in the social network. Here we show that the model converges upon a stable and compatible configuration. Then for the LP problem, it has been demonstrated that MWCLA produces much better results than other approaches compared to some state-of-the-art methods.

Automated analysis of video scenes requires the separation of moving objects from the background environment, which could not separate moving items from the background in the presence of noise. This paper presents a method to solve this challenge; this method uses the Directshow framework based on the pipe-and-filter architecture. This framework trace in three ways. In the first step, the values of the MSE, SNR, and PSNR criteria calculate. In this step, the results of the error criteria are compared with applying salt and pepper and Gaussian noise to images and then applying median, Gaussian, and Directshow filters. In the second step, the processing time for each method check in case of using median, Gaussian, and Directshow filter, and it will result that the used method in the article has high performance for real-time computing. In the third step, error criteria of foreground image check in the presence or absence of the Directshow filter. In the pipe-and-filter architecture, because filters can work asynchronously; as a result, it can boost the frame rate process, and the Directshow framework based on the pipe-and-filter architecture will remove the existing noise in the video at high speed. The results show that the used method is far superior to existing methods, and the calculated values for the MSE error criteria and the processing time decrease significantly. Using the Directshow, there are high values for the SNR and PSNR criteria, which indicate high-quality image restoration. By removing noise in the images, you could also separate moving objects from the background appropriately.

Following the development of wireless sensor networks, the need to design a low-waste, scalable, and long-life network is felt more than ever. Clustering and routing are widely used to minimize energy consumption and increase network lifetime, as important issues in wireless sensor networks. Since, in these networks, the largest amount of energy is spent on sending and receiving the data, the clustering technique done by collecting data on cluster heads has been found to influence the overall network performance; along with this, routine and efficient routing has also found to improve the network throughput. Therefore, multi-hop routing can increase the network lifetime and reduce the energy consumption by sensor nodes. In this paper, the main approach was using the mobile sinks attached to the public transportation vehicles, such as the bus to collect data in wireless sensor networks. The proposed protocol used multi-hop routing as well as Whale Optimization Algorithm to select cluster heads based on a fitness function, in which the amount of the remaining energy of the sensor nodes and the sum of the remaining energy of the adjacent sensor nodes were taken into account. Adopting this approach created a balance in the amount of energy consumption in sensor nodes. The proposed protocol was studied to validate the results obtained for the network lifetime and energy consumption. Independent and consecutive simulation results and statistical analysis indicates the superiority of the proposed protocol compared to other protocols. Also, the network lifetime improved by averagely 20% and the energy consumption reduced about 25% during the network activity.

This paper describes how to classify a data set by using an optimum set of exemplar to determine the label of an instance among a set of data for solving classification run time problem in a large data set. In this paper, we purposely use these exemplars to classify positive and negative bags in synthetic data set.There are several methods to implement multi-instance learning (MIL) such as SVM, CNN, and Diverse density. In this paper, optimum set of classifier exemplar (OSCE) is used to recognize positive bag (contains tumor patches). The goal of this paper is to find a way to speed up the classifier run time by choosing a set of exemplars. We used linear programming problems to optimize a hinge loss cost function, in which estimated label and actual label is used to train the classification. Estimated label is calculated by measuring Euclidean distance of a query point to all of its k nearest neighbors and an actual label value. To select some exemplars with none zero weights, Two solutions is suggested to have a better result. One of them is choosing k closer neighbors. The other one is using LP and thresholding to select some maximum of achieved unknown variable which are more significant in finding a set of exemplar. Also, there is trade-off between classifier run time and accuracy. In large data set, OSCE classifier has better performance than ANN and K-NN cluster. Also, OSCE is faster than NN classifier. After describing OSCE method, we used it to recognize a data set which contains cancer in synthetic data points. In deed, we define OSCE to apply for MIL for cancer detection.

For people that need total or partial assistance to perform daily tasks, assistive robots are one of the solutions. Force control of these robots when interact with human or manipulate objects, is one the challenging problems in this area. In this paper a ROS-based force control system is implemented on a JACO assistive robot for grasping tasks. This robot is specifically designed for people with upper body disorders. However, the robot can be used for public use and used for specific tasks that require high precision. To do this, we need to know exactly how the robot's internal performance works and how it is structured. It is usually achieved by designing sophisticated control techniques that meet these criteria. Advanced control architectures such as torque computation control allow tracking of desired paths with high accuracy, however, the need to integrate robotic models remains. The work presented in this study provides a basis for applying these techniques to the JACO robotic arm. The calculation is based on the Euler-Lagrange method of calculating the internal energy. The results are then analyzed to ensure the models estimated with control schemes. Therefore, more advanced analysis and control techniques can be implemented on this robotic arm. Finally, this study can be controlled by PID with respect to the torque entered to the end effector by the object so that the robotic arm can move from the initial position to the secondary position with optimum capture and torque control of all robot joints. The experimental results showed the effectiveness of proposed method to perform grasping and manipulation scenario successfully.

Grid is a new generation of distributed networks and allows users to share files like the Internet. With regard to the specific features of Grid environments, such as high dynamicity and resource/members heterogeneity, there are some challenges dealing to it. One of the most important services in grid environments is the resource discovery. The purpose of resource discovery is to identify a list of available resources for assigning to tasks. In this paper, using the assignment of prime numbers as the weight for tree nodes, and combining the hierarchical and super-peer structure, a new algorithm is presented with multiple trees. The results of the experiments and comparison with the previous methods indicate the improvement of the proposed method in terms of the number of visited nodes during the search process and the reduction of processing load caused by the smaller number of weights in the indexing tree.